TY - GEN
T1 - Hyperspectral imaging and spectral-spatial classification for cancer detection
AU - Fei, Baowei
AU - Akbari, Hamed
AU - Halig, Luma V.
PY - 2012/12/1
Y1 - 2012/12/1
N2 - Hyperspectral imaging is an emerging technology for biomedical applications. In this study, an advanced image processing and classification method is proposed to analyze hyperspectral image data for prostate cancer detection. Least squares support vector machines (LS-SVMs) were developed and evaluated for classifying hyperspectral data in order to enhance the detection of cancer tissue. The method was used to detect prostate cancer in tumor-bearing mice. Spatially resolved images were created to highlight the differences of the reflectance properties of cancer versus those of normal tissue. Preliminary results in mice show that the hyperspectral imaging and classification method was able to reliably detect prostate tumors in the animal model. The hyperspectral imaging technique may provide a new tool for optical diagnosis of cancer.
AB - Hyperspectral imaging is an emerging technology for biomedical applications. In this study, an advanced image processing and classification method is proposed to analyze hyperspectral image data for prostate cancer detection. Least squares support vector machines (LS-SVMs) were developed and evaluated for classifying hyperspectral data in order to enhance the detection of cancer tissue. The method was used to detect prostate cancer in tumor-bearing mice. Spatially resolved images were created to highlight the differences of the reflectance properties of cancer versus those of normal tissue. Preliminary results in mice show that the hyperspectral imaging and classification method was able to reliably detect prostate tumors in the animal model. The hyperspectral imaging technique may provide a new tool for optical diagnosis of cancer.
KW - Hyperspectral imaging
KW - prostate cancer detection
KW - spectral-spatial classification
KW - support vector machine
UR - http://www.scopus.com/inward/record.url?scp=84886380334&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84886380334&partnerID=8YFLogxK
U2 - 10.1109/BMEI.2012.6513047
DO - 10.1109/BMEI.2012.6513047
M3 - Conference contribution
AN - SCOPUS:84886380334
SN - 9781467311816
T3 - 2012 5th International Conference on Biomedical Engineering and Informatics, BMEI 2012
SP - 62
EP - 64
BT - 2012 5th International Conference on Biomedical Engineering and Informatics, BMEI 2012
T2 - 2012 5th International Conference on Biomedical Engineering and Informatics, BMEI 2012
Y2 - 16 October 2012 through 18 October 2012
ER -